Mining Actuarial Risk Predictors in Accident Descriptions Using Recurrent Neural Networks

Jean-Thomas Baillargeon, Luc Lamontagne and Etienne Marceau
Additional contact information
Jean-Thomas Baillargeon: Department of Computer Science and Software Engineering, Université Laval, Québec, QC G1V 0A6, Canada
Luc Lamontagne: Department of Computer Science and Software Engineering, Université Laval, Québec, QC G1V 0A6, Canada
Etienne Marceau: School of Actuarial Science, Université Laval, Québec, QC G1V 0A6, Canada

Risks, 2020, vol. 9, issue 1, 1-14

Abstract: One crucial task of actuaries is to structure data so that observed events are explained by their inherent risk factors. They are proficient at generalizing important elements to obtain useful forecasts. Although this expertise is beneficial when paired with conventional statistical models, it becomes limited when faced with massive unstructured datasets. Moreover, it does not take profit from the representation capabilities of recent machine learning algorithms. In this paper, we present an approach to automatically extract textual features from a large corpus that departs from the traditional actuarial approach. We design a neural architecture that can be trained to predict a phenomenon using words represented as dense embeddings. We then extract features identified as important by the model to assess the relationship between the words and the phenomenon. The technique is illustrated through a case study that estimates the number of cars involved in an accident using the accident’s description as input to a Poisson regression model. We show that our technique yields models that are more performing and interpretable than some usual actuarial data mining baseline.

Keywords: data mining; unstructured data; insurance big data; data representation; hierarchical attention neural networks; representational learning; natural language processing (search for similar items in EconPapers)
JEL-codes: C G0 G1 G2 G3 K2 M2 M4 (search for similar items in EconPapers)
Date: 2020
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.mdpi.com/2227-9091/9/1/7/pdf (application/pdf)
https://www.mdpi.com/2227-9091/9/1/7/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jrisks:v:9:y:2020:i:1:p:7-:d:469884

Access Statistics for this article

Risks is currently edited by Mr. Claude Zhang

More articles in Risks from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().